INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ills

-0.17

 ÑģÑĤÐ°Ð½Ð¾Ð²

-0.15

PRESENT

-0.14

 Scal

-0.14

.onCreate

-0.14

 Vend

-0.14

ILLS

-0.13

ubar

-0.13

empor

-0.13

ASS

-0.13

POSITIVE LOGITS

ardi

0.17

à¤Ĥà¤ľà¤¨

0.16

_tF

0.16

uitka

0.15

andaÅŁ

0.15

AXB

0.14

_mB

0.14

WWW

0.14

ocu

0.14

.Alignment

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.